Structural Indexing: Efficient 3-D Object Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
A Method for Registration of 3-D Shapes
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
Numerical recipes in C (2nd ed.): the art of scientific computing
Numerical recipes in C (2nd ed.): the art of scientific computing
Zippered polygon meshes from range images
SIGGRAPH '94 Proceedings of the 21st annual conference on Computer graphics and interactive techniques
Optimal Registration of Object Views Using Range Data
IEEE Transactions on Pattern Analysis and Machine Intelligence
Registration and Integration of Multiple Object Views for 3D Model Construction
IEEE Transactions on Pattern Analysis and Machine Intelligence
Point Signatures: A New Representation for 3D Object Recognition
International Journal of Computer Vision
The digital Michelangelo project: 3D scanning of large statues
Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Surface registration by matching oriented points
NRC '97 Proceedings of the International Conference on Recent Advances in 3-D Digital Imaging and Modeling
Surface reconstruction and display from range and color data
Surface reconstruction and display from range and color data
Fast and accurate shape-based registration
Fast and accurate shape-based registration
A Fast Automatic Method for Registration of Partially-Overlapping Range Images
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Registration of point cloud data from a geometric optimization perspective
Proceedings of the 2004 Eurographics/ACM SIGGRAPH symposium on Geometry processing
Registration of Multiple Point Sets
ICPR '96 Proceedings of the 13th International Conference on Pattern Recognition - Volume 2
Global registration of multiple 3D point sets via optimization-on-a-manifold
SGP '05 Proceedings of the third Eurographics symposium on Geometry processing
SGP '05 Proceedings of the third Eurographics symposium on Geometry processing
| Hi-index | 0.00 |
We propose a new algorithm for registering 3D scans obtained from different views of an object. Our work differs from the popular ICP based approach since we minimize error in signed distance function instead of squared distance between sampled surface points themselves. Our experiments show that this yields a fast and robust method of registering 3D scans into a single 3D model, firstly by simplifying point correspondence step, secondly by requiring fewer registration steps and lastly by using nonlinear optimization (the Levenberg-Marquardt algorithm) for error minimization, making the registration converge in fewer iterations. Our approach is also independent of the sampling resolution and works well in the presence of noise. We also believe that the distance-based error formulation lends itself much better for simultaneous registration of multiple overlapping views.